Publication number | US6397166 B1 |

Publication type | Grant |

Application number | US 09/187,406 |

Publication date | May 28, 2002 |

Filing date | Nov 6, 1998 |

Priority date | Nov 6, 1998 |

Fee status | Lapsed |

Publication number | 09187406, 187406, US 6397166 B1, US 6397166B1, US-B1-6397166, US6397166 B1, US6397166B1 |

Inventors | Ying Tat Leung, Menachem Levanoni, Sanjay E. Ramaswamy |

Original Assignee | International Business Machines Corporation |

Export Citation | BiBTeX, EndNote, RefMan |

Patent Citations (9), Non-Patent Citations (1), Referenced by (108), Classifications (6), Legal Events (5) | |

External Links: USPTO, USPTO Assignment, Espacenet | |

US 6397166 B1

Abstract

A method and system for grouping multiple data points, each data point being a set (e.g., a vector, a tuple, etc.) including a measured dependent value and at least one related independent variable value, include fitting the data into a model relating the independent and dependent variables of the data, and calculating similarity and distance between the data points and groups of the data points, thereby to group the multiple data points.

Claims(31)

1. A method of grouping multiple data points, each data point being a set comprising a measured dependent value and at least one related independent variable value, comprising:

fitting the data points into a model relating the independent and dependent variables of the data points;

calculating similarity and distance between said data points and groups of said data points; and

based on calculated similarity and distance, determining whether to group the multiple data points.

2. The method according to claim 1 , wherein said calculating similarity between first and second data points includes:

appending two data sets together and performing a least square regression fit for an assumed model form using the logarithm of observed sales data and markdown data, wherein if the data sets have n entries each, then the model being fitted in the log space is lnY=lnA+γm+β+lnε, where Y is a vector of size 2n, A is a matrix of [a_{1 }a_{2}], where a_{1 }is a base sale for data set **1** and a_{2 }is a base sale for data set **2**, m is a corresponding vector of markdowns, γ is a shared price sensitivity factor, and β is a vector of n shared seasonal indices;

using an adjusted regression coefficient R^{2 }obtained from the fit for the similarity measure, wherein R^{2 }is defined as 1-SSE/SS_{yy}, where SS_{yy}=Σ(y_{i}−{overscore (y)})^{2}, y being a mean of all observations of y, and SSE=Σ(y_{i}−ŷ)^{2}, where ŷ is a predicted value of y, based on the least square model fit, and adjusted R^{2}=1−(1−R^{2})*(n−1)/(n−1−c), where n is a number of observations, and c is a number of coefficients estimated; and

using a value **100*** R^{2 }as the similarity measure between the two data sets.

3. The method according to claim 1 , further comprising determining centers of groups of said data points.

4. The method according to claim 3 , wherein said determining said centers of said groups includes:

appending together the data sets corresponding to all the entities assigned to a group, and performing a least square regression;

assuming m entities with n data elements each, using a model fitted in log space of lnY=lnA+γM+β+lnε, where Y is a vector of size mn, A is a matrix of [a_{1 }a_{2 }. . . a_{m}], with a_{1 }being a base sale for data set **1** and a_{m }being a base sale for data set m, M is a corresponding vector of markdowns, γ is a shared price sensitivity factor, and β is a vector of n shared seasonal indices;

determining R^{2}=1−(1−R^{2})*(n−1)/(n−1−c), where n is a number of observations, and c is a number of coefficients estimated, as a measure of average group score; and

determining the similarity measure between the element and the center by one of using an array [β, γ] to define the group center, and scoring each element of the group against the center, such that the element with the highest measure is designated as the center.

5. The method according to claim 3 , wherein said calculating a similarity measure between first and second groups of data points, includes:

scoring each element of each group against the center thereof by finding the similarity measure between the element and the center, and using the element with the highest measure as the center; and

calculating the similarity measure between the centers of two groups.

6. The method according to claim 1 , wherein a distance between groups is determined by 100−the similarity measure.

7. A system for grouping multiple data points, each data point being a set comprising a measured dependent value and at least one related independent variable value, comprising:

means for fitting the data into a model relating the independent and dependent variables of the data;

means for calculating similarity and distance between said data points and groups of said data points; and

means for determining, based on calculated similarity and distance, whether to group the multiple data points.

8. The system according to claim 7 , wherein said means for calculating said similarity measure between first and second data points includes:

means for appending two data sets together and performing a least square regression fit for an assumed model form using the logarithm of observed sales data and markdown data, wherein if the data sets have n entries each, then the model being fitted in the log space is lnY=lnA+γm+β+lnε, where Y is a vector of size 2n, A is a matrix of [a_{1 }a_{2}], where a_{1 }is a base sale for data set **1** and a_{2 }is a base sale for data set.**2**, m is a corresponding vector of markdowns, γ is a shared price sensitivity factor, and β is a vector of n shared seasonal indices;

means for using an adjusted regression coefficient R^{2 }obtained from the fit for the similarity measure, wherein R^{2 }is defined as 1-SSE/SS_{yy}, where SS_{yy}=Σ(y_{i}−{overscore (y)})^{2}, y being a mean of all observations of y, and SSE=Σ(y_{i}−ŷ)^{2}, where ŷ is a predicted value of y, based on the least square model fit, and adjusted R^{2}=1−(1−R^{2})*(n−1)/(n−1−c), where n is a number of observations, and c is a number of coefficients estimated; and

means for using a value **100*** R^{2 }is used as the similarity measure between the two data sets.

9. The system according to claim 7 , further comprising means for determining centers of groups of said data points.

10. The system according to claim 9 , wherein said means for calculating said centers of said groups includes:

means for appending together the data sets corresponding to all the entities assigned to a cluster, and performing a least square regression;

assuming m entities with n data elements each, means for using a model fitted in log space of in lnY=lnA+γM+β+lnε, where Y is a vector of size mn, A is a matrix of [a_{1 }a_{2 }. . . a_{m}], with a_{1 }being a base sale for data set **1** and a_{m }being a base sale for data set m, M is a corresponding vector of markdowns, γ is a shared price sensitivity factor, and β is a vector of n shared seasonal indices;

means for determining R^{2}=1−(1−R^{2})*(n−1)/(n−1−c), where n is a number of observations, and c is a number of coefficients estimated, as a measure of average group score; and

means for determining the similarity measure between the element and the center by one of using an array [β, γ] to define the group center, and scoring each element of the group against the center, such that the element with the highest measure is designated as the center.

11. The system according to claim 7 , wherein said means for calculating a similarity measure between first and second groups of data points, includes:

means for scoring each element of each group against the center thereof by finding the similarity measure between the element and the center, and using the element with the highest measure as the center; and

means for calculating the similarity measure between the centers of two groups.

12. The system according to claim 7 , wherein a distance between groups is determined by 100−the similarity measure.

13. A signal-bearing medium tangibly embodying a program of machine-readable instructions executable by a digital processing apparatus to perform a method for computer-implemented model-based grouping of multiple data points, each data point being a set comprising a measured dependent value and at least one related independent variable value, said method comprising:

fitting the data into a model relating the independent and dependent variables of the data;

calculating similarity and distance between said data points and groups of said data points; and

based on calculated similarity and distance, determining whether to group the multiple data points.

14. The signal-bearing medium according to claim 13 , wherein said determining said similarity measure between first and second data points includes:

appending two data sets together and performing a least square regression fit for an assumed model form using the logarithm of observed sales data and markdown data, wherein if the data sets have n entries each, then the model being fitted in the log space is lnY=lnA+γm+β+lnε, where Y is a vector of size 2n, A is a matrix of [a_{1 }a_{2}], where a_{1 }is a base sale for data set **1** and a_{2 }is a base sale for data set **2**, m is a corresponding vector of markdowns, γ is a shared price sensitivity factor, and β is a vector of n shared seasonal indices;

using an adjusted regression coefficient R^{2 }obtained from the fit for the similarity measure, wherein R^{2 }is defined as 1-SSE/SS_{yy}, where SS_{yy}=Σ(y_{i}−{overscore (y)})^{2}, y being a mean of all observations of y, and SSE=Σ(y_{i}−ŷ)^{2}, where ŷ is a predicted value of y, based on the least square model fit, and adjusted R^{2}=1−(1−R^{2})*(n−1)/(n−1−c), where n is a number of observations, and c is a number of coefficients estimated; and

using the value **100*** R^{2 }as the similarity measure between the two data sets.

15. The signal-bearing medium according to claim 13 , further comprising determining centers of groups of said data points.

16. The signal-bearing medium according to claim 15 , wherein said determining said centers of said groups includes:

appending together the data sets corresponding to all entities assigned to a cluster, and performing a least square regression;

assuming m entities with n data elements each, using a model fitted in log space of lnY=lnA+γM+β+lnε, where Y is a vector of size mn, A is a matrix of [a_{1 }a_{2 }. . . a_{m}], with a_{1 }being a base sale for data set **1** and a_{m }being a base sale for data set m, M is a corresponding vector of markdowns, γ is a shared price sensitivity factor, and β is a vector of n shared seasonal indices;

determining R^{2}=1−(1−R^{2})*(n−1)/(n−1−c), where n is a number of observations, and c is a number of coefficients estimated, as a measure of average group score; and

determining the similarity measure between the element and the center by one of using an array [β, γ] to define the group center, and scoring each element of the group against the center, such that the element with the highest measure is designated as the center.

17. The signal-bearing medium according to claim 15 , wherein said calculating a similarity measure between first and second groups of data points, includes:

scoring each element of each group against the center thereof by finding the similarity measure between the element and the center, and using the element with the highest measure as the center; and

calculating the similarity measure between the centers of two groups.

18. The signal-bearing medium according to claim 13 , wherein a distance between groups is determined by 100−the similarity measure.

19. A method of model-based clustering, comprising:

initializing clustering parameters for a plurality of items;

providing a data set for clustering, and cluster center seeds, and calculating an target number of clusters;

incrementing an iteration counter;

scoring each item in the data set against all available cluster centers using a similarity measure process, wherein if a similarity measure value of the item being examined is greater than a minimum first parameter, no further search is performed for the item, and the item is assigned to a particular cluster, and when the similarity measure value is less than said minimum first parameter, the item is assigned to the cluster against which the item scores the highest;

removing clusters having a predetermined low number of assigned items, said removed clusters including items which are unassigned;

updating cluster centers for all remaining clusters;

calculating an overall average cluster score as the average of all the average cluster scores to determine an overall distance, an overall distance being recorded for each iteration performed;

determining whether an iteration is an odd-numbered iteration, wherein if it is determined that the iteration is an odd numbered iteration and that the remaining number of clusters is less than twice the target number calculated, then for each cluster checking a splitting criterion; and

determining whether a cluster is a candidate for splitting based on whether 100−average cluster score is greater than the overall distance, and whether the cluster has more than twice the minimum number of items needed, wherein an item which scores the least by having a lowest similarity measure against the cluster center is used as a seed for a new cluster to be formed.

20. The method according to claim 19 , further comprising:

assigning all items to clusters using the similarity measure calculation;

determining whether the iteration is an even-numbered iteration, wherein for even-numbered iterations, joining of clusters is attempted, and each cluster is scored against another by using finding a similarity measure between two clusters, and for each cluster a most similar cluster is found;

checking the similarity measure against a parameter, wherein if the similarity score is higher, then that pair of clusters are combined into one cluster by using any one of the centers;

assigning all items to clusters based on said similarity measure; and

checking the iteration number against a maximum iteration parameter, wherein if the iteration number is less than said maximum iteration parameter, the iteration number is incremented, and a sequence is repeated, and wherein if it is determined that the iteration is greater than the maximum iteration parameter, then the process terminates,

wherein the iteration with the lowest overall distance is selected, and corresponding assignments of items to clusters, the cluster scores and parameter estimates are used.

21. The method according to claim 19 , wherein said initializing comprises:

providing user-input values for the parameters including at least one of the maximum number of clustering iterations to be performed, the minimum number of items needed to form a cluster, the minimum score needed to stop searching and assign an item to a cluster, and the minimum score needed to combine two clusters; and

initializing dimensions of arrays used to read the data set.

22. The method according to claim 19 , wherein said cluster center seeds are used as initial cluster centers.

23. The method according to claim 19 , wherein said method is applied to retail transactions, and

wherein said determining said similarity measure between first and second entities includes:

appending two data sets together and performing a least square regression fit for an assumed model form using the logarithm of observed sales data and markdown data, wherein if the data sets have n entries each, then the model being fitted in the log space is lnY=lnA+γm+β+lnε, where Y is a vector of size 2n, A is a matrix of [a_{1 }a_{2}], where a_{1 }is a base sale for data set **1** and a_{2 }is a base sale for data set **2**, m is a corresponding vector of markdowns, γ is a shared price sensitivity factor, and β is a vector of n shared seasonal indices;

using an adjusted regression coefficient R^{2 }obtained from the fit for the similarity measure, wherein R^{2 }is defined as 1-SSE/SS_{yy}, where SS_{yy}=Σ(y_{i}−{overscore (y)})^{2}, y being a mean of all observations of y, and SSE=Σ(y_{i}−ŷ)^{2}, where ŷ is a predicted value of y, based on the least square model fit, and adjusted R^{2}=1−(1−R^{2})*(n−1)/(n−1−c), where n is a number of observations, and c is a number of coefficients estimated; and

using the value **100*** R^{2 }as the similarity measure between the two data sets.

24. The method according to claim 19 , wherein said updating cluster centers for remaining clusters includes:

appending together data sets corresponding to all the entities assigned to a cluster and performing a least square regression, wherein if there are m entities with n data elements each, then the model fitted in the log space is lnY=lnA+γM+β+lnε, where Y is a vector of size mn, A is a matrix of [a_{1 }a_{2 }. . . a_{m}], a_{1 }being a base sale for data set **1** and a_{m }being a base sale for data set m), M is a corresponding vector of markdowns, γ is a shared price sensitivity factor, and β is a vector of n shared seasonal indices;

determining adjusted , R^{2}=1−(1−R^{2})*(n−1)/(n−1−c), where n is a number of observations, and c is a number of coefficients estimated, R^{2 }being one of a measure of compactness of the cluster and an average cluster score; and

one of using an array [β, γ] to define the cluster center, and scoring each element of the cluster against the center by determining a similarity measure between the element and the center, and selecting the item with the highest measure as the center.

25. The method according to claim 24 , wherein said process of finding a similarity measure between first and second clusters, includes:

scoring each element of each cluster against the center by finding the similarity measure between the element and the center, and using the item with the highest measure as the center; and

calculating the similarity measure between the centers of two clusters.

26. The method according to claim 19 , wherein a distance between clusters is determined by 100−the similarity measure.

27. In a model-based clustering process for a plurality of data points, a method of determining a similarity measure between first and second data points of said plurality of data points includes:

appending two data sets together and performing a least square regression fit for an assumed model form using the logarithm of the observed sales data and the markdown data, wherein if the data sets have n entries each, then the model being fitted in the log space is lnY=lnA+γm+β+lnε, where Y is a vector of size 2n, A is a matrix of [a_{1 }a_{2}], where a_{1 }is a base sale for data set **1** and a_{2 }is a base sale for data set **2**, m is a corresponding vector of markdowns, γ is a shared price sensitivity factor, and β is a vector of n shared seasonal indices;

using an adjusted regression coefficient R^{2 }obtained from the fit for the similarity measure, wherein R^{2 }is defined as 1-SSE/SS_{yy}, where SS_{yy}=Σ(y_{i}−{overscore (y)})^{2}, y being a mean of all the observations of y, and SSE=Σ(y_{i}−ŷ)^{2}, where ŷ is a predicted value of y, based on the least square model fit, and adjusted R^{2}=1−(1−R^{2})*(n−1)/(n−1−c), where n is a number of observations, and c is a number of coefficients estimated; and

using the value **100*** R^{2 }as the similarity measure between the two data sets.

28. In a model-based clustering process for a plurality of clusters of data, a method of calculating a similarity measure between first and second clusters of data, includes:

determining centers of each of said first and second clusters;

scoring each element of each cluster against a center by finding the similarity measure between the element and the center, and using the element with the highest measure as the center; and

calculating the similarity measure between the centers of two clusters.

29. The method according to claim 28 , wherein said determining said centers of said groups includes:

appending together the data sets corresponding to all the entities assigned to a cluster, and performing a least square regression;

assuming m entities with n data elements each, using a model fitted in log space of lnY=lnA+γM+β+lnε, where Y is a vector of size mn, A is a matrix of [a_{1 }a_{2 }. . . a_{m}], with a_{1 }being a base sale for data set **1** and a_{m }being a base sale for data set m, M is a corresponding vector of markdowns, γ is a shared price sensitivity factor, and β is a vector of n shared seasonal indices;

determining R^{2}=1−(1−R^{2})*(n−1)/(n−1−c), where n is a number of observations, and c is a number of coefficients estimated, as a measure of average cluster score; and

determining the similarity measure between the element and the center by one of using an array [β, γ] to define the cluster center, and scoring each element of the cluster against the center, such that the element with the highest measure is designated as the center.

30. The method according to claim 28 , wherein a distance between clusters is determined by 100−the similarity measure.

31. The method according to claim 1 , wherein said model is defined by

where

Y=observed sales,

m=observed markdown (m=((regular price−observed price)/regular price), where regular price is a given constant); and the parameters include:

γ: Price sensitivity;

β: Seasonal index for the given time period; and

ε: Error term−1n(ε) is assumed to be normally distributed with mean 0, variance σ^{2}.

Description

1. Field of the Invention

The present invention generally relates to a computer-implemented method for clustering retail sales data, and more particularly to a method which assumes a model of retail demand as a function, for example, of the price, base sales rate, and seasonal factors, and clusters together items that have, for example, the same seasonal and price effect factors based on the model fit.

2. Description of the Related Art

Conventional systems utilize clustering for the construction of a classification scheme over a set of objects such that objects within classes are similar in some respects but are different from those in other classes.

The basic data for cluster analysis is a set of N entities for each of which p attribute values have been observed (e.g., N retail items for each of which the last 52 weeks of sales has been observed). The major features of cluster analysis include:

Choice of variables—This feature deals with determining which attributes of the elements to be clustered will be considered.

Measurement of similarity or distance—Most clustering techniques begin with a calculation of a matrix of similarities or distances between the entities to determine their “closeness” for clustering. Additionally, a measure of similarity should be definable between groups. Some typical choices are Euclidean distance, city block distance, Minkowski distance, and similarity coefficients based on the Pearson or Spearman correlation coefficients, as discussed for example in Kaufman et al., “Finding Groups in Data-An Introduction to Cluster Analysis”, John Wiley & Sons, 1990.

Generation of clusters—All clustering techniques attempt to partition the data set into a set of clusters such that individuals in a cluster have high similarity to one another and differ from those in other clusters. Similarity is defined quantitatively as discussed above. A number of techniques exist for clustering and differ in the approaches used for initiating clusters, searching through the solution space for target clusters, and the termination criterion. Some known clustering techniques relevant to the present invention include:

Hierarchical clustering: Given n objects, hierarchical clustering consists of a series of clustering from the initial situation when each object may be considered a singleton cluster to the other extreme where all objects belong to one cluster. Hierarchical techniques may be subdivided into agglomerative methods which proceed by a series of successive fusions of the n objects into groups, and divisive methods which partition the set of n entities successively into finer partitions.

Optimization techniques: Optimization techniques attempt to form an optimal k-partition over the given set of objects (i.e., divide the set of entities into k mutually exclusive clusters) to optimize a pre-defined objective function, where k is usually input by the user. The pre-defined objective function is usually a measure for maximizing similarity within the cluster and the distance between clusters. The techniques employed differ in the methods by which an initial partition of the data is obtained, and the method for iteratively searching for the optimal partition.

Other techniques include density search, fuzzy clustering, neural networks, and conceptual clustering, as described, for example, in B. Everitt, “Cluster Analysis”, Third Edition, Edward Arnold, 1993.

The term model-based clustering has also been used in another context, as described in Banfield et al., “Model-Based Gaussian and Non-Gaussian Clustering”, *Biometrics, *49, 803-822, 1993. This approach assumes a probability model for the population of interest and a density function for the observations.

In practical applications, among the popular methods for clustering are hierarchical- and optimization-based techniques, as mentioned above, which can be used to cluster retail sales data based on differences in the time series. Other applications of clustering can be found in a range of areas from finance (e.g., clustering stock price movement data) to the social sciences (e.g., clustering data on people's responses and preferences).

However, currently available methods for clustering do not assume a model relating the independent and dependent variables, and are hence, for example, in a retail environment, restricted to grouping only on the basis of observed sales data. Therefore, separating items on the basis of price effects etc. on demand is impossible.

For example, consider the sales of two items (e.g., sales**1** and sales**2**) shown in FIG. **5**A. Looking only at the sales data, they appear similar in sales pattern over time (e.g., weeks, months, etc.), and as such, the items would be assumed to exhibit similar seasonal behavior. However, when other factors are also considered (e.g., such as price in FIG. **5**B), and a model relating the sales to the price is assumed, then differing seasonal patterns and differing price sensitivities may be shown (e.g., see FIG. **5**C). The conventional techniques do not provide for such consideration of other such variables. Instead, the conventional techniques factor only one variable.

Thus, conventional clustering techniques use only one stream of data (e.g., such as the sales data over time) and have no capability for factoring other data streams/variables, and thus may erroneously classify (e.g., cluster) items **1** and **2** as similar, when in fact the items are not similar.

In view of the foregoing and other problems of the conventional methods and techniques, an object of the present invention is to provide a method for grouping of data sets (e.g., not restricted to retail sales data, but described below simply as an example) in cases where the data set includes an observed or dependent value, and one or more controllable or independent values, based on a model relating the independent and dependent variables.

In a first aspect, a method of grouping multiple data points, each data point being a set (e.g., a vector, a “tuple”, etc.) comprising a measured dependent value and at least one related independent variable value, includes fitting the data into a model relating the independent and dependent variables of the data, and calculating a similarity and a distance between the data points and groups of the data points, thereby to group the multiple data points.

In a second aspect, a system for grouping multiple data points, each data point being a set (e.g., a vector, a “tuple”, etc.) comprising a measured dependent value and at least one related independent variable value, includes means for fitting the data into a model relating the independent and dependent variables of the data, and means for calculating similarity and distance between the data points and groups of the data points, thereby to group the multiple data points.

In a third aspect, a signal-bearing medium is provided tangibly embodying a program of machine-readable instructions executable by a digital processing apparatus to perform a method for computer-implemented model-based clustering for grouping multiple data points, each data point being a set (e.g., a vector, a “tuple”, etc.) comprising a measured dependent value and at least one related independent variable value, the program including fitting the data into a model relating the independent and dependent variables of the data, and calculating similarity and distance between the data points and groups of the data points, thereby to group the multiple data points.

In a fourth aspect, a method of model-based clustering, includes initializing clustering parameters for a plurality of items; reading-in an actual data set used for clustering, and reading cluster center seeds, and calculating an target number of clusters; incrementing an iteration counter; scoring each item in the data set against all the available cluster centers using a similarity measure process, wherein if a similarity measure value of the item being examined is greater than a minimum first parameter, no further search is performed for the item, and the item is assigned to a particular cluster, and when the similarity measure value is less than said minimum first parameter, the item is assigned to the cluster against which the item scores the highest; removing clusters having a predetermined low number of assigned items, the removed clusters including items which are unassigned; updating cluster centers for all the remaining clusters; calculating an overall average cluster score as the average of all the average cluster scores to determine an overall distance, an overall distance being recorded for each iteration performed; determining whether the iteration is an odd-numbered iteration, wherein if it is determined that the iteration is an odd numbered iteration and that the remaining number of clusters is less than twice the target number calculated, then for each cluster checking a splitting criterion; determining whether a cluster is a candidate for splitting based on whether 100−average cluster score>overall distance, and the cluster has more than twice the minimum number of items needed, wherein an item which scores the least by having a lowest similarity measure against the cluster center is used as a seed for a new cluster that is formed; and assigning all items to clusters using the similarity measure calculation.

The method according to the fourth aspect further includes determining whether the iteration is an even-numbered iteration, wherein for even-numbered iterations, joining of clusters is attempted, and each cluster is scored against the other using a process of finding the similarity between two clusters, and for each cluster a most similar cluster is found; checking the similarity measure against a parameter MINCOMBINE, wherein if the similarity score is higher, then that pair of clusters are combined into one cluster by using any one of the centers, and destroying the other cluster; assigning all items to clusters based on said similarity measure; checking the iteration number against a maximum iteration parameter, wherein if the iteration number is less than said maximum iteration parameter, the iteration number is incremented, and a sequence is repeated, and wherein if it is determined that the iteration is greater than the maximum iteration parameter, then the process terminates, wherein the iteration with the lowest overall distance is selected as the best, and the corresponding assignments of items to clusters, and the cluster scores and parameter estimates are used as the solution.

The method according to the present invention is especially useful in estimating demand model parameters and in decision-support related to price and promotion planning in the retail industry. Obviously, as would be known by one of ordinary skill in the art within the purview of this application, other applications and implementations are possible including clustering financial data where market prices, causal variables and a model form for the relationship is made available, or in the social sciences where quantitatively measurable responses are linked to controllable inputs and a model relating the variables is assumed.

As mentioned above, methods for clustering include hierarchical- and optimization-based techniques, which can be used to cluster retail sales data based on differences in the time series. The present invention allows usage of these methods to cluster data based on price sensitivity in addition to seasonal effects with reference to a given demand model.

As a result, the inventive method can reliably estimate demand model parameters and in decision-support related to price and promotion planning in the retail industry.

The foregoing and other objects, aspects and advantages will be better understood from the following detailed description of a preferred embodiment of the invention with reference to the drawings, in which:

FIGS. 1A-1B are flow diagrams illustrating a preferred method of the invention;

FIG. 2 illustrates an exemplary hardware platform for use with the method of the present invention illustrated in FIGS. 1A-1B and more specifically a schematic illustration of a computer system used with the invention;

FIG. 3 illustrates a digital data processing apparatus for using the method of the invention;

FIG. 4 illustrates a computer program product for storing the inventive program steps of the method of FIGS. 1A-1B;

FIG. 5A is a graph of first and second items with similar sales patterns over time;

FIG. 5B is a graph illustrating the items' sale price data over time; and

FIG. 5C illustrates the different seasonal pattern for the items, when combined with their sale price data (FIG. **5**B), reveals different seasonal patterns (FIG. 5C) (e.g., when an independent variable is considered with dependent variables).

Referring now to the drawings, and more particularly to FIGS. 1A-1B, a first preferred embodiment of the method of the present invention is illustrated.

Generally, as mentioned above, the present invention relates to a computer-implemented method for clustering data points, and an exemplary implementation is described below regarding the retail environment. Specifically, in the exemplary implementation, the present invention provides a method for clustering retail sales data, and in greater detail a method which assumes a model of retail demand as a function of, for example, the price, base sales rate, and seasonal factors of the retail items, and clusters together retail items that have the same seasonal and price effect factors based on the model fit.

As mentioned above, in contrast to looking only at the sales data as shown in FIG. 5A, the present invention considers other independent variables (e.g., such as, for example, in the retail environment, the price of sale for the items), and thus when a model relating the sales to the price is assumed, then differing seasonal patterns and differing price sensitivities are shown for the different items. Thus, looking at only one variable may lead to an erroneous decision to cluster data, whereas in the invention by relating the independent variables with the dependent variables, a truer, more reliable determination may be made as to whether to cluster first and second data points and groups.

FIG. 5C illustrates a graph revealing different seasonal patterns and different price sensitivities. The seasonal effects (e.g., multiplier) is seen along the Y axis and time (e.g., weeks, months, etc.) is shown along the X axis. Also shown is the price effect and price sensitivity factor. In the example, item **1** has a price sensitivity factor of 1 (e.g., a 10.5% increase for a 10% increase in markdown) and item **2** shows a price sensitivity factor of 3 (e.g., a 35% increase for a 10% increase in markdown). Thus, as shown the results of combining the sales data (FIG. 5A) with the sale price data (FIG. 5B) reveal different seasonal patterns (e.g., possibly due to traditional buying seasons, etc.), resulting in a more reliable determination as whether to group or cluster such data. In the case at hand, since the results are very different, a determination would likely be made not to cluster or group the data points.

Thus, as mentioned above, while conventional clustering techniques use only one stream of data (e.g., such as the sales data over time) and may thus classify items **1** and **2** as similar, the inventive model-based clustering approach uses a model to relate multiple streams of data (sales and price over time in the above example) and clusters or classifies only on the basis of similarity in terms of model effects.

As mentioned above, while the exemplary implementation has been directed to the retail industry, other applications, such as financial market data, social science data, etc. would find equal benefit with the invention.

Moreover, the method of the present invention differs from the conventional techniques in that the inventive method assumes a model to describe the relations between the observed attributes of each entity (item). In one exemplary implementation, observed sales and price data over a given time period are assumed to be related by a model of the form

^{γm}e^{β}ε (1)

where

Y=observed sales,

m=observed markdown (m=((regular price−observed price)/regular price), where regular price is a given constant); and the parameters include:

γ: Price sensitivity;

β: Seasonal index for the given time period; and

ε: Error term−ln(ε) is assumed to be normally distributed with mean 0, variance σ^{2}.

Using this model, the following measures of distance, similarity, and compactness are defined below.

Similarity Measure Between Two Entities

The similarity measure between two entities (e.g., each having n periods of sales and markdown observations) is calculated as follows.

First, the two data sets are appended together and a least square regression fit for the assumed model form (e.g., Equation 1 above) is made using the logarithm of the observed sales data and the markdown data.

If the data sets have n entries each, then the model being fitted in the log space is lnY=lnA+γM+β+lnε, where Y is a vector of size 2n, A is a matrix of [a_{1}, a_{2}] (e.g., a_{1 }being the base sale for data set **1** and a_{2 }being the base sale for data set **2** in log space, and base sale being the sales with no markdowns or seasonal effects (i.e., m and β=0), m is the corresponding vector of markdowns, γ is the shared price sensitivity factor, and β is the vector of n shared seasonal indices. All data with observed values of zero (i.e., Y=0) are ignored for this purpose.

Then, the adjusted regression coefficient R^{2 }obtained from the fit is used as the basis for the similarity measure.

For clarity, R^{2 }is defined as 1-SSE/SS_{yy}, where SS_{yy}=Σ(y_{i}−{overscore (y)})^{2}, with {overscore (y)} being the mean of all the observations of y. SSE=Σ(y_{i}−ŷ)^{2}, where ŷ is the predicted value of y, based on the least square model fit. Adjusted R^{2}=1−(1−R^{2})*(n−1)/(n−1−c), where n is the number of observations, and c is the number of coefficients estimated.

Then, the value **100*** R^{2 }is used as the similarity measure between the two data sets.

Cluster Centers and Compactness of Clusters

To determine the cluster centers and compactness of clusters, first the data sets corresponding to all the entities assigned to a cluster are appended together and a least square regression is done.

If there are m entities with n data elements each, then the model fitted in the log space is lnY=lnA+γM+β+lnε, where Y is a vector of size mn, A is a matrix of [a_{1 }a_{2 }. . . a_{m}] (a_{1 }being the base sale for data set 1 and a_{m }for data set m), M is the corresponding vector of markdowns, γ is the shared price sensitivity factor, and β is the vector of n shared seasonal indices. Once again, all data with observed values of sales being zero is ignored for this purpose.

Thereafter, adjusted R^{2}=1−(1−R^{2})*(n−1)/(n−1−c), where n is the number of observations, and c is the number of coefficients estimated. This R^{2 }is used as a measure of the “compactness” of the cluster or the average cluster score.

Then, the array [γ, β] is used to define the cluster center. Alternatively, each element of the cluster is scored against the center (e.g., the similarity measure between the element and the center is calculated), and the item with the highest measure is used as the center (e.g., designated as the center).

Similarity Measure Between Two Clusters

Each element of each cluster is scored against the center (e.g., the similarity measure between the element and the center is calculated), and the item with the highest measure is used as the center.

Then, the similarity measure between the centers of two clusters is calculated as described above in the manner of determining a similarity measure between two entities.

Distance

Then, distance is calculated. Distance is defined to be (100−similarity measure) for all cases. The distance could be between two entities or two clusters.

First Preferred Embodiment of Clustering Method

Using these measures, a clustering scheme based on the K-Mean and K-Median approaches (e.g., see Kaufman et al. “Finding Groups in Data—An Introduction to Cluster Analysis” John Wiley & Sons, 1990) has been implemented and tested. The flow chart of a preferred implementation is shown in FIGS. 1A-1B and as described below.

Turning to FIG. 1A, a clustering method **100** is shown.

First, in step **101**, initialization of the clustering parameters is performed. Initialization includes reading in user-input values for the parameters such as MAXITER (e.g., the maximum number of clustering iterations to be done), MINITEMS (e.g., the minimum number of items needed to form a cluster), MINSCORE (e.g., the minimum score needed to stop searching and assign an item to a cluster), and MINCOMBINE (e.g., the minimum score needed to combine two clusters). Other variables such as Iteration are also initialized to zero, and the dimensions of arrays used to read in the data set are initialized. The variables can be freely set and defined by the designer.

In step **102**, the actual data set used for clustering is read-in from input files, and the cluster center seeds (e.g., user-input) also are read. These seeds are used as the initial cluster centers. Given the number of elements, a calculation of the target number of clusters (e.g., NCLUST) is also made using standard methods available. For example, the number of clusters (NCLUST) is either input or calculated using a heuristic method, (e.g., NCLUST=Min (N, (0.375*N/(logN)^{2})).

In step **103**, the iteration counter is incremented.

In step **104**, each item in the data set is scored against all the available cluster centers using the similarity measure method detailed above.

If the similarity measure value (e.g., of the item being examined) is greater than MINSCORE, no further search is performed for the item, and it is assigned to the particular cluster without any further comparison to other clusters. Otherwise, the item is assigned to the cluster against which the item scores the highest.

In step **105**, clusters with very few assigned items (e.g., less than MINITEMS) are removed, and the items now remain unassigned.

In step **106**, cluster centers are updated for all the remaining clusters and averaging the cluster score. This updating is performed by executing the method specified above in the description of the determination of clusters centers and compactness of clusters.

In step **107**, the overall distance is computed. Specifically, an average cluster score is computed as the average of all the average cluster scores. Overall distance is then=100−overall average cluster score. The overall distance is used as a measure of the goodness (e.g., fitness) of all the clusters obtained in an iteration and is recorded for each iteration performed.

In step **108**, it is determined whether the iteration is an odd-numbered iteration. If it is determined that the iteration is an odd-numbered iteration and that the remaining number of clusters is less than twice the target number calculated (e.g., *NCLUST) (e.g., a “YES” in step **108**), then for each cluster a check of the splitting criterion is performed (e.g., steps **109** and **110**), as described below.

For example, based on steps **108**-**110**, if 100−average cluster score>overall distance, and the cluster has more than twice the minimum number of items needed (e.g., MINITEMS), then the cluster is considered a candidate for splitting and the process proceeds to step **111**.

Turning to FIG. **1**B and step **111**, the item which scores the least (e.g., the lowest similarity measure) against the cluster center is used as the seed for the new cluster that is formed.

In step **112**, an assignment of all items to clusters is performed using the similarity measure calculation (e.g., similar to step **104** above). Specifically, for all items, assign the item to a cluster with the highest similarity measure.

In step **113**, it is determined whether the iteration is an even-numbered iteration.

For even-numbered iterations, instead of splitting clusters, joining of clusters is attempted (e.g., see steps **114** and **115**). Specifically, each cluster is scored against the other using the method specified above in the description of finding the similarity between two clusters, and for each cluster a most similar cluster is found.

In step **116**, the similarity measure is checked against MINCOMBINE. In step **117**, if the similarity score is higher, then that pair of clusters are combined into one cluster by using any one of the centers, and destroying the other cluster. Thus, the profiles are merged.

In step **118**, an assignment of all items to clusters as in step **104** is performed.

In step **119**, the iteration number is checked against MAXITER. If the iteration number is less than MAXITER, then the process loops to step **103**, and the sequence is repeated.

If in step **119**, it is determined that the iteration is greater than MAXITER, then the process continues to step **120** and the procedure terminates. The iteration with the lowest overall distance is picked as the best, and the corresponding assignments of items to clusters, and the cluster scores and parameter estimates are used as the solution.

As described above, with the computer-implemented method of the invention, retail sales data can be clustered, and the method assumes a model of retail demand as a function of, for example, the price, base sales rate, and seasonal factors of the retail items. Thus, retail items that have the same seasonal and price effect factors can be clustered based on the model fit.

In contrast to the conventional techniques, the inventive method assumes a model to describe the relations between the observed attributes of each entity.

Further, the method of the present invention provides a model relating the independent and dependent variables, and provides a grouping which is not restricted and not based only on observed sales data. Finally, the invention can, for example, in a retail environment, separate items on the basis of price effects on demand.

The present invention may be implemented on a variety of different hardware platforms in a variety of different software environments.

A representative hardware environment for practicing the present invention is depicted in FIG. 2, which illustrates the typical hardware configuration of an information handling/computer system in accordance with the subject invention having at least one processor or central processing unit (CPU) **10**. CPUs **10** are interconnected via system bus **12** to a random access memory (RAM) **14**, read-only memory (ROM) **16**, an input/output (I/O) adapter **18** for connecting peripheral devices such as disk units **20** and tape drives **40** to bus **12**, user interface adapter **22** for connecting keyboard **24**, mouse **26**, speaker **28**, microphone **32**, and/or other user interface devices such as touch screen device (not shown) to bus **12**, communication adapter **34** for connecting the information handling system to a data processing network, and display adapter **36** for connecting bus **12** to display device **38**.

In addition to the hardware environment described above, a different aspect of the invention includes a computer-implemented method for model-based clustering. As an example, this method may be implemented in the particular hardware environment discussed above.

Such a method may be implemented, for example, by operating the computer system/processor **10** (FIG. **2**), as embodied by a digital data processing apparatus **30** (FIG. **3**), to execute a sequence of machine-readable instructions. These instructions may reside in various types of signal-bearing media.

Thus, this aspect of the present invention is directed to a programmed product, comprising signal-bearing media tangibly embodying a program of machine-readable instructions executable by a digital data processor to perform a method of model-based clustering.

This signal-bearing media may include, for example, a RAM (not shown) contained within the processor **10**, as represented by the fast-access storage **302**A for example. Alternatively, the instructions may be contained in another signal-bearing media, such as a magnetic data storage diskette **400**, as shown in FIG. 5, directly or indirectly accessible by the processor **10**.

Whether contained in the diskette **400**, the computer/processor **10**, or elsewhere, the instructions may be stored on a variety of machine-readable data storage media, such as DASD storage (e.g., a conventional “hard drive” or a RAID array)! magnetic tape, electronic read-only memory (e.g., ROM, EPROM, or EEPROM), an optical storage device (e.g. CD-ROM, WORM, DVD, digital optical tape, etc.), paper “punch” cards, or other suitable signal-bearing media including transmission media such as digital and analog and communication links and wireless. In an illustrative embodiment of the invention, the machine-readable instructions may comprise software object code, compiled from a language such as “C”, etc.

While the invention has been described in terms of preferred embodiments, those skilled in the art will recognize that the invention can be practiced with modification within the spirit and scope of the appended claims.

Patent Citations

Cited Patent | Filing date | Publication date | Applicant | Title |
---|---|---|---|---|

US6012058 * | Mar 17, 1998 | Jan 4, 2000 | Microsoft Corporation | Scalable system for K-means clustering of large databases |

US6021383 * | Oct 7, 1996 | Feb 1, 2000 | Yeda Research & Development Co., Ltd. | Method and apparatus for clustering data |

US6092072 * | Apr 7, 1998 | Jul 18, 2000 | Lucent Technologies, Inc. | Programmed medium for clustering large databases |

US6100901 * | Jun 22, 1998 | Aug 8, 2000 | International Business Machines Corporation | Method and apparatus for cluster exploration and visualization |

US6115708 * | Mar 4, 1998 | Sep 5, 2000 | Microsoft Corporation | Method for refining the initial conditions for clustering with applications to small and large database clustering |

US6122628 * | Oct 31, 1997 | Sep 19, 2000 | International Business Machines Corporation | Multidimensional data clustering and dimension reduction for indexing and searching |

US6236985 * | Oct 7, 1998 | May 22, 2001 | International Business Machines Corporation | System and method for searching databases with applications such as peer groups, collaborative filtering, and e-commerce |

US6263334 * | Nov 11, 1998 | Jul 17, 2001 | Microsoft Corporation | Density-based indexing method for efficient execution of high dimensional nearest-neighbor queries on large databases |

US6263337 * | May 22, 1998 | Jul 17, 2001 | Microsoft Corporation | Scalable system for expectation maximization clustering of large databases |

Non-Patent Citations

Reference | ||
---|---|---|

1 | Banfield, et. al., "Model-Based Gaussian and Non-Gaussian Clustering", Biometrics 49, pp. 803-821, Sep. 1993. |

Referenced by

Citing Patent | Filing date | Publication date | Applicant | Title |
---|---|---|---|---|

US6574585 * | Feb 26, 2001 | Jun 3, 2003 | International Business Machines Corporation | Method for improving robustness of weighted estimates in a statistical survey analysis |

US6640227 * | Sep 5, 2000 | Oct 28, 2003 | Leonid Andreev | Unsupervised automated hierarchical data clustering based on simulation of a similarity matrix evolution |

US6684177 * | May 10, 2001 | Jan 27, 2004 | Hewlett-Packard Development Company, L.P. | Computer implemented scalable, incremental and parallel clustering based on weighted divide and conquer |

US6826568 * | Dec 20, 2001 | Nov 30, 2004 | Microsoft Corporation | Methods and system for model matching |

US6834266 * | Oct 11, 2001 | Dec 21, 2004 | Profitlogic, Inc. | Methods for estimating the seasonality of groups of similar items of commerce data sets based on historical sales data values and associated error information |

US6847924 * | Jun 19, 2000 | Jan 25, 2005 | Ncr Corporation | Method and system for aggregating data distribution models |

US6907380 * | Dec 1, 2003 | Jun 14, 2005 | Hewlett-Packard Development Company, L.P. | Computer implemented scalable, incremental and parallel clustering based on weighted divide and conquer |

US6910017 | Mar 5, 1999 | Jun 21, 2005 | Profitlogic, Inc. | Inventory and price decision support |

US6960135 | Dec 5, 2001 | Nov 1, 2005 | Profitlogic, Inc. | Payout distributions for games of chance |

US6976001 * | Jun 29, 2000 | Dec 13, 2005 | International Business Machines Corporation | Method and apparatus suitable for demand forecasting |

US7006981 | Apr 4, 2001 | Feb 28, 2006 | Profitlogic, Inc. | Assortment decisions |

US7072902 * | Nov 26, 2002 | Jul 4, 2006 | Tzunami Inc | Method and system for organizing objects according to information categories |

US7085734 | Jul 6, 2001 | Aug 1, 2006 | Grant D Graeme | Price decision support |

US7171376 | Jul 14, 2004 | Jan 30, 2007 | Oracle International Corporation | Methods and apparatus for inventory allocation and pricing |

US7197435 * | Apr 2, 2004 | Mar 27, 2007 | Advanced Micro Devices, Inc. | Method and apparatus for using clustering method to analyze semiconductor devices |

US7237115 * | Sep 26, 2001 | Jun 26, 2007 | Sandia Corporation | Authenticating concealed private data while maintaining concealment |

US7251615 | Jun 7, 2002 | Jul 31, 2007 | Oracle International Corporation | Markdown management |

US7403928 | Feb 1, 2006 | Jul 22, 2008 | Siemens Power Transmission & Distribution, Inc. | Identify data sources for neural network |

US7437308 | Dec 20, 2004 | Oct 14, 2008 | Oracle International Corporation | Methods for estimating the seasonality of groups of similar items of commerce data sets based on historical sales date values and associated error information |

US7523117 | May 3, 2006 | Apr 21, 2009 | West Virginia University Research Corporation | Method for data clustering and classification by a graph theory model—network partition into high density subgraphs |

US7711734 * | Apr 5, 2007 | May 4, 2010 | Sas Institute Inc. | Systems and methods for mining transactional and time series data |

US7716022 | May 9, 2006 | May 11, 2010 | Sas Institute Inc. | Computer-implemented systems and methods for processing time series data |

US7752233 * | Mar 29, 2007 | Jul 6, 2010 | Massachusetts Institute Of Technology | Techniques for clustering a set of objects |

US7770072 * | Jan 16, 2007 | Aug 3, 2010 | Xerox Corporation | Method and system for analyzing time series data |

US7962804 | May 10, 2010 | Jun 14, 2011 | Xerox Corporation | Method and system for analyzing time series data |

US8005707 | May 9, 2006 | Aug 23, 2011 | Sas Institute Inc. | Computer-implemented systems and methods for defining events |

US8010324 | May 9, 2006 | Aug 30, 2011 | Sas Institute Inc. | Computer-implemented system and method for storing data analysis models |

US8014983 | Jun 22, 2010 | Sep 6, 2011 | Sas Institute Inc. | Computer-implemented system and method for storing data analysis models |

US8060512 * | Jun 5, 2009 | Nov 15, 2011 | Xerox Corporation | Hybrid tensor-based cluster analysis |

US8112302 | Aug 31, 2007 | Feb 7, 2012 | Sas Institute Inc. | Computer-implemented systems and methods for forecast reconciliation |

US8364517 | Dec 16, 2011 | Jan 29, 2013 | Sas Institute Inc. | Computer-implemented systems and methods for forecast reconciliation |

US8433171 | Jun 18, 2010 | Apr 30, 2013 | Corning Cable Systems Llc | High fiber optic cable packing density apparatus |

US8467651 | Sep 28, 2010 | Jun 18, 2013 | Ccs Technology Inc. | Fiber optic terminals configured to dispose a fiber optic connection panel(s) within an optical fiber perimeter and related methods |

US8520996 | Mar 31, 2010 | Aug 27, 2013 | Corning Cable Systems Llc | Removably mountable fiber optic terminal |

US8538226 | Oct 9, 2009 | Sep 17, 2013 | Corning Cable Systems Llc | Fiber optic equipment guides and rails configured with stopping position(s), and related equipment and methods |

US8542973 | Apr 20, 2011 | Sep 24, 2013 | Ccs Technology, Inc. | Fiber optic distribution device |

US8593828 | Mar 31, 2010 | Nov 26, 2013 | Corning Cable Systems Llc | Communications equipment housings, assemblies, and related alignment features and methods |

US8625950 | Dec 18, 2009 | Jan 7, 2014 | Corning Cable Systems Llc | Rotary locking apparatus for fiber optic equipment trays and related methods |

US8631040 | Feb 22, 2011 | Jan 14, 2014 | Sas Institute Inc. | Computer-implemented systems and methods for flexible definition of time intervals |

US8660397 | Nov 30, 2010 | Feb 25, 2014 | Corning Cable Systems Llc | Multi-layer module |

US8662760 | Oct 29, 2010 | Mar 4, 2014 | Corning Cable Systems Llc | Fiber optic connector employing optical fiber guide member |

US8699838 | Nov 9, 2011 | Apr 15, 2014 | Ccs Technology, Inc. | Fiber optic furcation module |

US8705926 | Nov 23, 2010 | Apr 22, 2014 | Corning Optical Communications LLC | Fiber optic housings having a removable top, and related components and methods |

US8706993 * | Sep 14, 2012 | Apr 22, 2014 | Commvault Systems, Inc. | Systems and methods for storage modeling and costing |

US8712206 | Apr 30, 2010 | Apr 29, 2014 | Corning Cable Systems Llc | High-density fiber optic modules and module housings and related equipment |

US8718436 | Aug 30, 2010 | May 6, 2014 | Corning Cable Systems Llc | Methods, apparatuses for providing secure fiber optic connections |

US8725980 | Sep 7, 2012 | May 13, 2014 | Commvault Systems, Inc. | System and method for allocation of organizational resources |

US8792767 | Apr 15, 2011 | Jul 29, 2014 | Ccs Technology, Inc. | Distribution device |

US8798427 | Oct 19, 2007 | Aug 5, 2014 | Corning Cable Systems Llc | Fiber optic terminal assembly |

US8879881 | Nov 24, 2010 | Nov 4, 2014 | Corning Cable Systems Llc | Rotatable routing guide and assembly |

US8879882 | Apr 26, 2011 | Nov 4, 2014 | Corning Cable Systems Llc | Variably configurable and modular local convergence point |

US8909019 | Oct 11, 2012 | Dec 9, 2014 | Ccs Technology, Inc. | System comprising a plurality of distribution devices and distribution device |

US8913866 | Mar 26, 2010 | Dec 16, 2014 | Corning Cable Systems Llc | Movable adapter panel |

US8953924 | Aug 29, 2012 | Feb 10, 2015 | Corning Cable Systems Llc | Removable strain relief brackets for securing fiber optic cables and/or optical fibers to fiber optic equipment, and related assemblies and methods |

US8985862 | Mar 15, 2013 | Mar 24, 2015 | Corning Cable Systems Llc | High-density multi-fiber adapter housings |

US8989547 | Jun 26, 2012 | Mar 24, 2015 | Corning Cable Systems Llc | Fiber optic equipment assemblies employing non-U-width-sized housings and related methods |

US8992099 | Mar 31, 2010 | Mar 31, 2015 | Corning Cable Systems Llc | Optical interface cards, assemblies, and related methods, suited for installation and use in antenna system equipment |

US8995812 | Oct 23, 2013 | Mar 31, 2015 | Ccs Technology, Inc. | Fiber optic management unit and fiber optic distribution device |

US9004778 | Jun 29, 2012 | Apr 14, 2015 | Corning Cable Systems Llc | Indexable optical fiber connectors and optical fiber connector arrays |

US9008485 | Apr 25, 2012 | Apr 14, 2015 | Corning Cable Systems Llc | Attachment mechanisms employed to attach a rear housing section to a fiber optic housing, and related assemblies and methods |

US9020320 | Jan 22, 2013 | Apr 28, 2015 | Corning Cable Systems Llc | High density and bandwidth fiber optic apparatuses and related equipment and methods |

US9022814 | Oct 11, 2012 | May 5, 2015 | Ccs Technology, Inc. | Sealing and strain relief device for data cables |

US9037998 | Jul 18, 2012 | May 19, 2015 | Sas Institute Inc. | Computer-implemented systems and methods for time series exploration using structured judgment |

US9038832 | Nov 29, 2012 | May 26, 2015 | Corning Cable Systems Llc | Adapter panel support assembly |

US9042702 | Sep 18, 2012 | May 26, 2015 | Corning Cable Systems Llc | Platforms and systems for fiber optic cable attachment |

US9047559 | Apr 5, 2012 | Jun 2, 2015 | Sas Institute Inc. | Computer-implemented systems and methods for testing large scale automatic forecast combinations |

US9049500 | Aug 31, 2012 | Jun 2, 2015 | Corning Cable Systems Llc | Fiber optic terminals, systems, and methods for network service management |

US9059578 | Feb 18, 2010 | Jun 16, 2015 | Ccs Technology, Inc. | Holding device for a cable or an assembly for use with a cable |

US9075216 | Nov 5, 2010 | Jul 7, 2015 | Corning Cable Systems Llc | Fiber optic housings configured to accommodate fiber optic modules/cassettes and fiber optic panels, and related components and methods |

US9075217 | Nov 23, 2010 | Jul 7, 2015 | Corning Cable Systems Llc | Apparatuses and related components and methods for expanding capacity of fiber optic housings |

US9087306 | Jul 13, 2012 | Jul 21, 2015 | Sas Institute Inc. | Computer-implemented systems and methods for time series exploration |

US9098553 * | Mar 15, 2013 | Aug 4, 2015 | Gridglo Llc | System and method for remote activity detection |

US9111220 | Mar 14, 2014 | Aug 18, 2015 | Commvault Systems, Inc. | Systems and methods for storage modeling and costing |

US9116324 | Nov 17, 2010 | Aug 25, 2015 | Corning Cable Systems Llc | Stacked fiber optic modules and fiber optic equipment configured to support stacked fiber optic modules |

US9147218 | Mar 6, 2013 | Sep 29, 2015 | Sas Institute Inc. | Devices for forecasting ratios in hierarchies |

US9152685 | Feb 24, 2014 | Oct 6, 2015 | Commvault Systems, Inc. | Systems and methods for migrating components in a hierarchical storage network |

US9164692 | May 5, 2014 | Oct 20, 2015 | Commvault Systems, Inc. | System and method for allocation of organizational resources |

US9195700 | Jan 30, 2013 | Nov 24, 2015 | United Services Automobile Association (Usaa) | Systems and methods for storing time-series data |

US20020183966 * | May 10, 2001 | Dec 5, 2002 | Nina Mishra | Computer implemented scalable, incremental and parallel clustering based on weighted divide and conquer |

US20030028437 * | Jul 6, 2001 | Feb 6, 2003 | Grant D. Graeme | Price decision support |

US20030074251 * | Oct 11, 2001 | Apr 17, 2003 | Mahesh Kumar | Clustering |

US20030104861 * | Dec 5, 2001 | Jun 5, 2003 | Peter Gaidarev | Payout distributions for games of chance |

US20030120651 * | Dec 20, 2001 | Jun 26, 2003 | Microsoft Corporation | Methods and systems for model matching |

US20030145002 * | Nov 26, 2002 | Jul 31, 2003 | Tzunami, Inc. | Method and system for organizing objects according to information categories |

US20030200134 * | Mar 28, 2003 | Oct 23, 2003 | Leonard Michael James | System and method for large-scale automatic forecasting |

US20030229502 * | Jun 7, 2002 | Dec 11, 2003 | Woo Jonathan W. | Markdown management |

US20040098412 * | Nov 3, 2003 | May 20, 2004 | International Business Machines Corporation | System and method for clustering a set of records |

US20040122797 * | Dec 1, 2003 | Jun 24, 2004 | Nina Mishra | Computer implemented scalable, Incremental and parallel clustering based on weighted divide and conquer |

US20050027621 * | Jun 4, 2004 | Feb 3, 2005 | Ramakrishnan Vishwamitra S. | Methods and apparatus for retail inventory budget optimization and gross profit maximization |

US20050027681 * | Aug 31, 2004 | Feb 3, 2005 | Microsoft Corporation | Methods and systems for model matching |

US20060053156 * | Sep 6, 2005 | Mar 9, 2006 | Howard Kaushansky | Systems and methods for developing intelligence from information existing on a network |

US20060184472 * | Feb 1, 2006 | Aug 17, 2006 | Dingguo Chen | Identify data sources for neural network |

US20060274062 * | May 3, 2006 | Dec 7, 2006 | Cun-Quan Zhang | Method for data clustering and classification by a graph theory model - network partition into high density subgraphs |

US20070239753 * | Apr 5, 2007 | Oct 11, 2007 | Leonard Michael J | Systems And Methods For Mining Transactional And Time Series Data |

US20080010304 * | Mar 29, 2007 | Jan 10, 2008 | Santosh Vempala | Techniques for clustering a set of objects |

US20080027930 * | Jul 31, 2006 | Jan 31, 2008 | Bohannon Philip L | Methods and apparatus for contextual schema mapping of source documents to target documents |

US20080112680 * | Nov 9, 2006 | May 15, 2008 | Mcgranahan Danny | Optical fiber slack storage for splice trays and splice assemblies |

US20080170507 * | Jan 16, 2007 | Jul 17, 2008 | Handley John C | Method and system for analyzing time series data |

US20100312797 * | Jun 5, 2009 | Dec 9, 2010 | Xerox Corporation | Hybrid tensor-based cluster analysis |

US20120288015 * | Jan 21, 2011 | Nov 15, 2012 | Thomson Licensing | Data pruning for video compression using example-based super-resolution |

US20130007402 * | Sep 14, 2012 | Jan 3, 2013 | Commvault Systems, Inc. | Systems and methods for storage modeling and costing |

US20130226922 * | Feb 27, 2013 | Aug 29, 2013 | International Business Machines Corporation | Identification of Complementary Data Objects |

US20140280208 * | Mar 15, 2013 | Sep 18, 2014 | Gridglo Llc | System and Method for Remote Activity Detection |

US20140372178 * | Jun 18, 2013 | Dec 18, 2014 | Target Brands, Inc. | Correlating product sales to store segmentation |

US20150169732 * | Dec 18, 2013 | Jun 18, 2015 | F. Michel Brown | Method for summarized viewing of large numbers of performance metrics while retaining cognizance of potentially significant deviations |

CN100456281C | May 25, 2006 | Jan 28, 2009 | 株式会社东芝 | Data division apparatus, data division method |

CN100592288C | Sep 28, 2005 | Feb 24, 2010 | 英特尔公司 | K-means clustering using t-test computation |

WO2006084151A2 * | Feb 2, 2006 | Aug 10, 2006 | Siemens Power Transm & Distrib | Identify data sources for neural network |

Classifications

U.S. Classification | 702/179 |

International Classification | G06F17/18 |

Cooperative Classification | G06F17/18, G06K9/6221 |

European Classification | G06K9/62B1P1, G06F17/18 |

Legal Events

Date | Code | Event | Description |
---|---|---|---|

Nov 6, 1998 | AS | Assignment | Owner name: INTERNATIONAL BUSINESS MACHINES CORPORATION, NEW Y Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:LEUNG, YING TAT;LEVANONI, MENACHEM;RAMASWAMY, SANJAY E.;REEL/FRAME:009585/0695 Effective date: 19981105 |

Sep 14, 2005 | FPAY | Fee payment | Year of fee payment: 4 |

Jan 4, 2010 | REMI | Maintenance fee reminder mailed | |

May 28, 2010 | LAPS | Lapse for failure to pay maintenance fees | |

Jul 20, 2010 | FP | Expired due to failure to pay maintenance fee | Effective date: 20100528 |

Rotate